Submission Deadline: 31 December 2026 View: 31 Submit to Special Issue
Prof. Dr. Esteban Díaz
Email: esteban.diaz@ua.es
Affiliation: Departamento de Ingeniería Civil, Escuela Politécnica Superior, Universidad de Alicante, Alicante, Spain
Research Interests: data-driven and machine learning methods for geotechnical prediction, ensemble learning, deep neural networks, symbolic regression and interpretable machine learning, probabilistic modeling and uncertainty quantification, ground improvement and jet grouting performance prediction, advanced finite element modeling in geotechnical engineering, foundation settlement analysis, soil compressibility behavior, swelling behavior of fine-grained soils, remote sensing and InSAR-based ground deformation monitoring, geohazard assessment using geospatial and machine learning techniques
Dr. Panpan Guo
Email: guopanpan@hfut.edu.cn
Affiliation: School of Civil Engineering, Hefei University of Technology, Hefei, China
Research Interests: ground improvement, artificial intelligence technologies, deep excavations, tunnelling, underground space technologies
Prof. Dr. Rubén Galindo Aires
Email: rubenangel.galindo@upm.es
Affiliation: Department of Geotechnical Engineering, Escuela de Caminos, Canales y Puertos, Universidad Politécnica de Madrid, Madrid, Spain
Research Interests: rock mechanics, soil dynamics, foundations, numerical methods, data science
This Special Issue gathers recent advances in artificial intelligence (AI) for geotechnical engineering, covering site investigation, soil property prediction, deformation and stability forecasting, and decision support in design and construction. Increasing project complexity and richer monitoring and characterization data are driving the need for robust, transferable models. AI can complement established methods by capturing non-linear behaviour, integrating heterogeneous information, and enabling fast predictions when repeated analyses are needed.
We invite original contributions that develop, validate, or benchmark AI methods for geotechnical problems across laboratory, field, and infrastructure scales. Submissions should show methodological rigor and engineering relevance, with emphasis on robustness and transferability, interpretable predictions, and practical value for design, assessment, or monitoring. Studies addressing data quality, geotechnically meaningful features, and uncertainty-aware learning are also welcome.
Submissions on physics-informed machine learning (ML) and digital-twin-enabled workflows are especially welcome, particularly when they show reliable performance with limited data and clear integration into monitoring or decision-making. We also encourage emerging approaches such as graph neural networks and Transformer-based models for spatial and temporal geotechnical data.
Topics of interest include, but are not limited to, AI/ML applied to:
• Site investigation, subsurface characterization, and data fusion.
• Soil and rock behaviour characterization and parameter identification.
• Foundations, earth structures, and retaining systems.
• Ground improvement techniques.
• Deformation forecasting and monitoring-driven assessment.
• Underground works and tunnelling.
• Geohazards, early warning, and risk mitigation.
• Problematic geomaterials (expansive/collapsible soils, organic soils, uncontrolled fills).
• Groundwater flow and coupled processes.
Login
Register
Submit a Paper
Propose a Special lssue